You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, thanks for the nice code~
I have some questions about the pseudo-labels training part of the code,
this is the pseudo labeling loss of the source data as Eq.11 in paper: loss_seg1 = self.update_variance(labels, pred1, pred2), in which the labels come from the source domain.
the target domain does not use the pseudo-labels but the entropy minimization: loss_kl = ( self.kl_loss(self.log_sm(pred_target2) , mean_pred) + self.kl_loss(self.log_sm(pred_target1) , mean_pred))/(nhw)
The text was updated successfully, but these errors were encountered:
jingzhengli
changed the title
Question about Pseudo-labels are source domain but not target domain in the cod
Question about Pseudo-labels are source domain but not target domain in the code
Jun 3, 2021
Hi, thanks for the nice code~
I have some questions about the pseudo-labels training part of the code,
this is the pseudo labeling loss of the source data as Eq.11 in paper:
loss_seg1 = self.update_variance(labels, pred1, pred2), in which the labels come from the source domain.
the target domain does not use the pseudo-labels but the entropy minimization:
loss_kl = ( self.kl_loss(self.log_sm(pred_target2) , mean_pred) + self.kl_loss(self.log_sm(pred_target1) , mean_pred))/(nhw)
The text was updated successfully, but these errors were encountered: